Annuaire des serveurs MCP
54,429 serveurs MCP qui relient les assistants IA à des outils et des données, issus du registre MCP officiel et des listes communautaires, mis à jour toutes les heures.
- 16 catégories
- 34,659 serveurs distants
- Mis à jour toutes les heures
io.github.stabgan/steelmindio.github.stabgan/steelmind
Structured thinking + steel-manning verification for AI agents. Backed by 43+ papers.
io.github.joepangallo/web-recon-agentio.github.joepangallo/web-recon-agent
Owned-target web security assessment MCP server for authenticated, high-friction apps.
io.github.0xbrainkid/agentfolio-mcp-serverio.github.0xbrainkid/agentfolio-mcp-server
AI agent identity verification via SATP on Solana. Trust scores and on-chain attestations.
io.github.operantlabs/operant-mcpio.github.operantlabs/operant-mcp
Security testing MCP server for penetration testing, forensics, and vulnerability assessment
io.github.kastelldev/kastellio.github.kastelldev/kastell
Server security audit (413 checks), hardening, and fleet management across 4 cloud providers.
io.github.leochong/visus-mcpio.github.leochong/visus-mcp
Security-first web access for Claude. Sanitizes pages, blocks injection, redacts PII.
io.github.jnMetaCode/shellwardio.github.jnMetaCode/shellward
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
io.github.Brano80/Veridion-nexusio.github.Brano80/Veridion-nexus
Veridion Nexus MCP server - GDPR Art. 44-49 runtime compliance for AI agents
io.github.rog0x/depio.github.rog0x/dep
License check, outdated deps, security for AI agents
io.github.omoshola-o/xapio.github.omoshola-o/xap
Agent settlement protocol — discover, negotiate, settle, and verify with XAP.
io.github.titus-civic/mcp-gatewayio.github.titus-civic/mcp-gateway
Identity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.
io.github.mintmas/oracle42-intelligenceio.github.mintmas/oracle42-intelligence
AI-powered threat intelligence, smart contract auditing, and cybersecurity OSINT.
io.github.Aguantar/vibescan-mcp-serverio.github.Aguantar/vibescan-mcp-server
MCP server for VibeScan — scan projects for leaked secrets and security issues
io.github.RobotFleet-HQ/security-orchestraio.github.RobotFleet-HQ/security-orchestra
Multi-agent MCP platform for data centers and critical power.
io.github.mastrophot/contract-security-scannerio.github.mastrophot/contract-security-scanner
MCP smart contract scanner with NEAR-focused security context.
io.github.bx33661/wireshark-mcpio.github.bx33661/wireshark-mcp
Professional network analysis with tshark. Security audits, deep-dives, and threat detection.
Velvoite — EU Financial Regulatory Complianceeu.velvoite/compliance
EU financial regulatory monitoring: DORA, MiCA, MiFID II, AML, Solvency II and more.
io.github.yb48666-ctrl/otr-protocolio.github.yb48666-ctrl/otr-protocol
Merchant trust verification for AI agents. One call = trust score, badge, and purchase safety.
com.keyboardcrumbs/mcpcom.keyboardcrumbs/mcp
Live threat intel for Claude — CVE, KEV predictions, IP lookup, malware hashes. Free, no API key.
io.github.russellshen1992/2oio.github.russellshen1992/2o
Human intelligence API — AI agents verify facts with human domain experts via MCP
io.github.DownAtTheBottomOfTheMoleHole/megalinterio.github.DownAtTheBottomOfTheMoleHole/megalinter
MCP server for running Ox Security MegaLinter via mega-linter-runner
io.github.lordbasilaiassistant-sudo/base-security-scanner-mcpio.github.lordbasilaiassistant-sudo/base-security-scanner-mcp
MCP server to scan smart contracts on Base for honeypots, rug pulls, and vulnerabilities.
io.github.pdaxt/pqvaultio.github.pdaxt/pqvault
Post-quantum secrets manager for AI agents. ML-KEM-768 + X25519 + AES-256-GCM.
io.github.beautyfree/app-store-connectio.github.beautyfree/app-store-connect
App Store Connect API as MCP: apps, TestFlight, subscriptions, localizations, reports. JWT auth.
ai.imboard/dossierai.imboard/dossier
MCP server for dossier automation standard - enables LLMs to discover, verify, and execute dossiers
io.github.bighippoman/license-complianceio.github.bighippoman/license-compliance
Scan npm dependencies for license compliance issues. Catch GPL contamination.
io.github.mifactory-bot/mifactory-logic-verifierio.github.mifactory-bot/mifactory-logic-verifier
Verify AI agent reasoning and logic for errors and contradictions. Pay-per-use.
io.github.BurtTheCoder/virustotalio.github.BurtTheCoder/virustotal
MCP server for querying VirusTotal API with comprehensive security analysis tools.
io.github.inkog-io/inkogio.github.inkog-io/inkog
Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.
io.github.shotwellj/air-blackboxio.github.shotwellj/air-blackbox
EU AI Act compliance scanner for Python AI agents — scan, analyze, and remediate
io.github.Bajuzjefe/aikido-mcpio.github.Bajuzjefe/aikido-mcp
Security analysis for Aiken smart contracts on Cardano. 75 vulnerability detectors.
io.github.mcp-protocol/node-runtimeio.github.mcp-protocol/node-runtime
This package is intended for demonstration only. Maintained by JFrog Security.
io.github.ogSINGH/contrast-checker-mcpio.github.ogSINGH/contrast-checker-mcp
MCP - WCAG 2.1 color contrast checker - contrast ratios, compliance and accessible color suggestions
io.github.bountyyfi/mcp-watchdogio.github.bountyyfi/mcp-watchdog
MCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.
net.agentutil/verify-mcpnet.agentutil/verify-mcp
Sub-cent factual claim verification against live data sources.
com.636865636b73756d/mcp-v1com.636865636b73756d/mcp-v1
Sub-cent factual claim verification against live data sources.
io.github.ertugrulakben/dep-oracleio.github.ertugrulakben/dep-oracle
Predictive dependency security engine. Trust scores, zombie detection, blast radius analysis.
io.github.torkjacobs/tork-governanceio.github.torkjacobs/tork-governance
AI agent governance for MCP: PII detection, policy enforcement, compliance, and kill switch.
io.github.rsdouglas/janeeio.github.rsdouglas/janee
Secure secrets proxy for AI agents — manages API keys so agents never see raw credentials.
com.arcself/arc-securitycom.arcself/arc-security
Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.
io.github.oogdevs/clawtube-mcpio.github.oogdevs/clawtube-mcp
Minimal MCP server for ClawTube — a small, auditable control plane for skills and agents.
io.github.365xbusiness/vigo-mcpio.github.365xbusiness/vigo-mcp
AI-powered Hong Kong SFC regulatory intelligence. Bilingual EN/ZH compliance queries.
io.github.ExpertVagabond/guardrailsio.github.ExpertVagabond/guardrails
AI Agent Guardrails MCP server - security layer
io.github.Dave-London/pare-npmio.github.Dave-London/pare-npm
Pare npm ג€” Structured npm/pnpm operations (install, audit, outdated, list, run) as typed JSON.
io.github.Dave-London/pythonio.github.Dave-London/python
Structured Python tool output (ruff, mypy, pip-audit, pip-install) as typed JSON.
io.github.Dave-London/npmio.github.Dave-London/npm
Structured npm/pnpm operations (install, audit, outdated, list) as typed JSON.
io.github.vibegpt/policycheckio.github.vibegpt/policycheck
AI seller verification and policy risk analysis for any online store.
io.github.tb0hdan/wass-mcpio.github.tb0hdan/wass-mcp
MCP server for web application security scanning
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données. Dernière synchronisation 29 oct. 2026.
Questions fréquentes
Qu’est-ce que MCP ?
Le Model Context Protocol est un standard ouvert qui permet à un assistant IA (Claude, ChatGPT, Cursor, un agent) d'appeler des outils et de lire des données externes via un « serveur ». Un serveur distant est une URL à ajouter à votre client ; un serveur local tourne sur votre ordinateur à partir d'un paquet (npm, PyPI, Docker).
Comment ajouter un serveur MCP à Claude ou Cursor ?
Ouvrez la page du serveur ici, copiez son bloc de configuration dans le fichier de réglages MCP de votre client, puis redémarrez-le. Un serveur distant n'a besoin que de l'URL ; un serveur local demande Node (npx), Python (uvx) ou Docker.
Ces serveurs sont-ils sûrs ?
N'importe qui peut publier dans le registre. Un serveur peut lire ce à quoi vous lui donnez accès et agir en votre nom : préférez ceux dont le code est public et l'éditeur reconnu, et accordez le minimum de droits.